WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning

Sangwoo Lee; Sunghwan Park; Jaewoo Lee

cs.LGJul 7, 2026

WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning

Authors: Sangwoo Lee, Sunghwan Park, Jaewoo Lee

Organizations: Chung-Ang University, Seoul, South Korea

Abstract

Label skew in federated learning (FL) causes client drift and degrades global accuracy. Synthetic data augmentation can reduce this imbalance; however, full class balancing requires substantial computation cost. We propose FedEAS, a policy that assigns each client an entropy-adaptive per-class generation budget computed from its local label distribution. The budget jointly decides \emph{how much} each client generates and \emph{WHERE} the samples go. Accordingly, the total generation budget follows from the per-client budgets rather than being fixed in advance. FedEAS recovers most of the accuracy gain of full class balancing while reducing the generation budget by 94.1%. At the same total generation budget, it outperforms Uniform allocation by up to 18.82% across CIFAR-10 and CIFAR-100.

Explore similar work

FedReLa: Imbalanced Federated Learning via Re-Labeling
Jun 24, 2026Guangzheng Hu, Patricia Menéndez, Feng Liu +3Federated Learning Class Imbalance
Class-wise Contribution Estimation via Logit Maximization for Federated Learning
Date pendingAsim Ukaye, Nurbek Tastan, Mubarak Abdu-Aguye +1Federated Learning Logit Lens
FedRAW: Preserving Rare-Label Influence in Asynchronous Federated Learning
Sep 7, 2026Prashant Bajpai, Divya Saxena, Philippe Lalanda +1Federated Learning Candidate Label Distributions

Jun 24, 2026 · stat.MLJ/K move · Enter open · S save

FedReLa: Imbalanced Federated Learning via Re-Labeling

Guangzheng Hu, Patricia Menéndez, Feng Liu, Mingming Gong+2

Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation. The global class imbalance and cross-client data heterogeneity naturally coexist, and the mismatch between local and global imbalances exacerbates the performance degradation of the aggregated model. The agnosticism of global class distribution poses significant challenges for data-level methods, especially under extreme conditions with severe class absence across clients. In this paper, we propose FedReLa, a novel data-level approach that tackles the coexistence of data heterogeneity and class imbalance in federated learning. By re-labeling samples with a feature-dependent label re-allocator, FedReLa corrects biased global decision boundaries without requiring knowledge of the global class distribution. This modular, model-agnostic approach can be integrated with algorithmic methods to deliver consistent improvements without additional communication overhead. Through extensive experiments, our method significantly improves the accuracy of minority classes and the overall accuracy on stepwise-imbalanced and long-tailed datasets, outperforming the previous state of the art.

Federated Learning Class Imbalance Fedavg Candidate Label Distributions Heterogeneity

Open paper Ask about it PDF

Abstract

Explore similar work

FedReLa: Imbalanced Federated Learning via Re-Labeling

Class-wise Contribution Estimation via Logit Maximization for Federated Learning

FedRAW: Preserving Rare-Label Influence in Asynchronous Federated Learning